English
Related papers

Related papers: Commutativity in the Algorithmic Lovasz Local Lemm…

200 papers

The Lov\'asz hinge is a convex surrogate recently proposed for structured binary classification, in which $k$ binary predictions are made simultaneously and the error is judged by a submodular set function. Despite its wide usage in image…

Machine Learning · Computer Science 2022-03-18 Jessie Finocchiaro , Rafael Frongillo , Enrique Nueve

We consider supervised learning problems in which set predictions provide explicit uncertainty estimates. Using Choquet integrals (a.k.a. Lov{\'a}sz extensions), we propose a convex loss function for nondecreasing subset-valued functions…

Machine Learning · Computer Science 2025-12-23 Francis Bach

Local feature selection in machine learning provides instance-specific explanations by focusing on the most relevant features for each prediction, enhancing the interpretability of complex models. However, such methods tend to produce…

Machine Learning · Computer Science 2024-07-17 Harrie Oosterhuis , Lijun Lyu , Avishek Anand

A pattern $\alpha$ is a string of variables and terminal letters. We say that $\alpha$ matches a word $w$, consisting only of terminal letters, if $w$ can be obtained by replacing the variables of $\alpha$ by terminal words. The matching…

Data Structures and Algorithms · Computer Science 2021-06-14 Paweł Gawrychowski , Florin Manea , Stefan Siemer

We compare alternative computing strategies for solving the constrained lasso problem. As its name suggests, the constrained lasso extends the widely-used lasso to handle linear constraints, which allow the user to incorporate prior…

Machine Learning · Statistics 2016-11-08 Brian R. Gaines , Hua Zhou

It has been shown that the nonreversible overdamped Langevin dynamics enjoy better convergence properties in terms of spectral gap and asymptotic variance than the reversible one. In this article we propose a variance reduction method for…

Probability · Mathematics 2017-01-23 Romain Poncet

The LASSO is an attractive regularisation method for linear regression that combines variable selection with an efficient computation procedure. This paper is concerned with enhancing the performance of LASSO for square-free hierarchical…

Methodology · Statistics 2023-05-10 Shaoxiong Hu , Hugo Maruri-Aguliar , Zixiang Ma

We present polynomial-time algorithms for approximate counting and sampling solutions to constraint satisfaction problems (CSPs) with atomic constraints within the local lemma regime: $$ pD^{2+o_q(1)}\lesssim 1. $$ When the domain size $q$…

Data Structures and Algorithms · Computer Science 2024-04-05 Chunyang Wang , Yitong Yin

We present theoretical guarantees for an alternating minimization algorithm for the dictionary learning/sparse coding problem. The dictionary learning problem is to factorize vector samples $y^{1},y^{2},\ldots, y^{n}$ into an appropriate…

Machine Learning · Statistics 2019-08-01 Niladri S. Chatterji , Peter L. Bartlett

The use of machine learning methods for predictive purposes has increased dramatically over the past two decades, but uncertainty quantification for predictive comparisons remains elusive. This paper addresses this gap by extending the…

Econometrics · Economics 2025-05-09 Juan Carlos Escanciano , Ricardo Parra

Composite likelihood has shown promise in settings where the number of parameters $p$ is large due to its ability to break down complex models into simpler components, thus enabling inference even when the full likelihood is not tractable.…

Methodology · Statistics 2021-07-21 Claudia Di Caterina , Davide Ferrari

When machine learning systems meet real world applications, accuracy is only one of several requirements. In this paper, we assay a complementary perspective originating from the increasing availability of pre-trained and regularly…

We study randomized algorithms for constrained optimization, in abstract frameworks that include, in strictly increasing generality: convex programming; LP-type problems; violator spaces; and a setting we introduce, consistent spaces. Such…

Computational Geometry · Computer Science 2019-06-04 Kenneth L. Clarkson , Bernd Gärtner , Johannes Lengler , May Szedlak

Countless variants of the Lempel-Ziv compression are widely used in many real-life applications. This paper is concerned with a natural modification of the classical pattern matching problem inspired by the popularity of such compression…

Data Structures and Algorithms · Computer Science 2011-04-22 Pawel Gawrychowski

In this article, we study the problem of sampling from distributions whose densities are not necessarily smooth nor logconcave. We propose a simple Langevin-based algorithm that does not rely on popular but computationally challenging…

Machine Learning · Statistics 2025-12-02 Tim Johnston , Iosif Lytras , Nikolaos Makras , Sotirios Sabanis

We point out a close connection between the Moser-Tardos algorithmic version of the Lov\'asz Local Lemma, a central tool in probabilistic combinatorics, and the cluster expansion of the hard core lattice gas in statistical mechanics. We…

Mathematical Physics · Physics 2013-06-18 Rogério Gomes Alves , Aldo Procacci

We propose a sampling algorithm that achieves superior complexity bounds in all the classical settings (strongly log-concave, log-concave, Logarithmic-Sobolev inequality (LSI), Poincar\'e inequality) as well as more general settings with…

Statistics Theory · Mathematics 2023-06-29 Jiaojiao Fan , Bo Yuan , Yongxin Chen

We introduce a learning-based algorithm to obtain a measurement matrix for compressive sensing related recovery problems. The focus lies on matrices with a constant modulus constraint which typically represent a network of analog phase…

Signal Processing · Electrical Eng. & Systems 2021-10-15 Michael Koller , Wolfgang Utschick

We present a new algorithm for general reinforcement learning where the true environment is known to belong to a finite class of N arbitrary models. The algorithm is shown to be near-optimal for all but O(N log^2 N) time-steps with high…

Machine Learning · Computer Science 2013-08-23 Tor Lattimore , Marcus Hutter , Peter Sunehag

We introduce prox-convex for minimizing $F(x)=g(x)+h(C(x))+s(R(x))$, where $g$ and $h$ are convex, $C$ and $s$ are smooth, and each component of $R$ is convex (possibly nonsmooth). Here $g$ captures general convex objectives and indicator…

Optimization and Control · Mathematics 2025-12-24 Samet Uzun , Dayou Luo , Behçet Açıkmeşe , Aleksandr Y. Aravkin